BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Opportunistic Spectrum Access with Multiple Users: Learning under 
 Competition - Anima Anandkumar - MIT
DTSTART:20100331T100000Z
DTEND:20100331T110000Z
UID:TALK24014@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:*Abstract:* The problem of cooperative allocation among multip
 le secondary users to avoid collisions in a cognitive radio network is con
 sidered. The channel availability statistics are initially unknown to all 
 the secondary users and are learnt via sensing samples. Distributed learni
 ng and allocation schemes which minimize the total regret of the users whe
 n compared with the ideal scenario with known availability statistics and 
 centralized allocation are proposed. The first scheme assumes minimal prio
 r information in terms of pre-allocated ranks for allocation while the sec
 ond scheme is fully distributed and assumes no prior information at the us
 ers. The two schemes have sum regret which is provably logarithmic in the 
 total number of access slots. A lower bound is derived for any learning sc
 heme which is asymptotically logarithmic in the number of slots. Hence\, o
 ur schemes achieve asymptotic order optimality in terms of regret in learn
 ing and allocation. \n\n*Biography:* I hail from Mysore\, India. I receive
 d her B.Tech in Electrical Engineering from the Indian Institute of Techno
 logy Madras in 2004 and my M.S. and Ph.D in Electrical and Computer Engine
 ering from Cornell University in 2009. At Cornell\, I worked at the adapti
 ve communications and signal processing (ACSP) group with Prof. Lang Tong 
 as advisor. I have spent summers at the networking technologies group\, IB
 M Watson Research\, Hawthorne\, NY. I am currently a post-doctoral researc
 her at the Stochastic Systems Group working with Prof. Alan Willsky. I wil
 l be joining EECS Dept.\, University of California Irvine as an assistant 
 professor starting July 2010. \n\nMy research interests are in the area of
  statistical signal processing\, networking and information theory. I have
  worked on inference and learning of graphical models\, scalable algorithm
 s and asymptotic analysis. I am the recipient of the IEEE Signal Processin
 g Society (SPS) 2008 Young Author award\, 2007-08 IBM Fran Allen PhD fello
 wship\, 2006-07 Google Anita Borg award finalist and the student paper awa
 rd at the 2006 Intl. Conf. on Acoustic\, Speech and Signal Processing (ICA
 SSP).\n\n
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR